research-automation

Tag

Cards List
#research-automation

@tom_doerr: Automates research workflows with persistent multi-agent memory https://github.com/EvoScientist/EvoScientist…

X AI KOLs Timeline ↗ · 2026-05-09 Cached

EvoScientist is an open-source framework that automates research workflows using self-evolving AI scientists with persistent multi-agent memory, adopting a human-on-the-loop paradigm for autonomous research exploration and insight generation.

0 favorites 0 likes
#research-automation

@ManusAI: https://x.com/ManusAI/status/2052764534872678882

X AI KOLs Following ↗ · 2026-05-08 Cached

The article explains how Manus's Browser Operator works by operating inside the user's authorized local browser session, allowing it to access subscription-based and authenticated content beyond typical AI search capabilities, and provides a step-by-step guide for enabling and using it.

0 favorites 0 likes
#research-automation

@RoundtableSpace: HUGGING FACE JUST AUTOMATED THEIR ENTIRE POST-TRAINING TEAM WITH AN AGENT. It reads papers, runs GPU experiments, itera…

X AI KOLs Following ↗ · 2026-04-21 Cached

Hugging Face replaced its post-training team with an autonomous agent that reads papers, runs GPU experiments, and improves models, achieving a 22-point benchmark jump in under 10 hours and beating Codex on HealthBench by 60%.

0 favorites 0 likes
#research-automation

@lftherios: 1/ Autoresearch from @karpathy has been one of the most interesting agentic patterns to emerge this year. The challenge…

X AI KOLs Timeline ↗ · 2026-04-20 Cached

Andrej Karpathy's autoresearch pattern highlights how current AI agents run experiments in isolation, wasting compute by duplicating work and rediscovering dead ends.

0 favorites 0 likes
#research-automation

Import AI 455: AI systems are about to start building themselves.

Hacker News Top ↗ · 2026-05-21 Cached

The article argues that there is a high likelihood (60%+) of fully automated AI R&D—where AI systems can build their own successors without human involvement—by the end of 2028, citing evidence from coding benchmarks like SWE-Bench and trends in AI autonomy.

1 favorites 1 likes
← Previous
← Back to home

Submit Feedback